© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 271
    Prev
    Next
    INDEX
    Explanations

    describing essense or standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diversas
    0.18
     andra
    0.17
     thiab
    0.16
     forskellige
    0.16
     an
    0.16
     ulike
    0.16
     आणि
    0.15
    2
    0.15
    曜日
    0.15
             
    0.15
    POSITIVE LOGITS
     failings
    0.17
     arrhythmia
    0.16
     wrongdoing
    0.16
     strugg
    0.15
     transgression
    0.15
    もので
    0.14
    에서의
    0.14
     knockdown
    0.14
     onslaught
    0.14
     offender
    0.14
    Activations Density 5.229%

    No Known Activations